AI Model Evaluator & Rubric Specialist

Role description

Evaluate frontier LLM responses against structured multi-criteria rubrics, write detailed justification rationales, and identify factual or instruction-following failures across generalist and domain prompts.

Requirements & qualification

Strong analytical writing in English, disciplined instruction following, ability to separate verifiable facts from model hallucinations, and comfort grading complex pairwise comparisons.

Verify ongoing project availability, regional rules, and assessment steps on the official platform or employer page.